AI Paper Atlas

Research map / Detection and segmentation / CNN features

Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection

Peng Zhang, Tingfa Xu, Shuaihao Han, Jianan Li

ECCV 2026 · Detection and segmentation › CNN features · approach: Box regression and loss design · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add rotation-equivariant group convolutions (ablation)YOLOv8n-style baseline · MODAmAP: 43.3 -> 47.7Improved
add SpeIW (ablation)equivariant baseline · MODAmAP: 47.7 -> 50.3Improved
add ReCoW (ablation)equivariant baseline · MODAmAP: 47.7 -> 49.6Improved
add oriented-aware head (ablation)equivariant baseline · MODAmAP: 47.7 -> 49.3Improved
add oriented-aware head and ReCoW to SpeIW (ablation)equivariant + SpeIW · MODAmAP: 50.3 -> 54.3Improved
replace discrete RE-DCN spectral operators with SpeIW (ablation)FressDet · MODAmAP: 53.2 -> 54.3Improved
use SpeIW instead of plain C4-CNN (ablation)FressDet · MODAmAP: 52.1 -> 54.3Improved
use MSI input instead of RGBFressDet · MODAmAP: 50.6 -> 54.3Improved
soft spectral and hard spatial routing instead of soft-soft (ablation)ReCoW · MODAmAP: 52.4 -> 54.3Improved
soft spectral routing instead of hard-hard (ablation)ReCoW · MODAmAP: 51.2 -> 54.3Improved
agreement gate instead of addition fusion (ablation)ReCoW · MODAmAP: 52.8 -> 54.3Improved
use both spectral and spatial branches instead of spectral only (ablation)ReCoW · MODAmAP50: 72.3 -> 73.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy